CN110674411B - Public opinion propagation model based on media and interpersonal influence and propagation method thereof - Google Patents
Public opinion propagation model based on media and interpersonal influence and propagation method thereof Download PDFInfo
- Publication number
- CN110674411B CN110674411B CN201810706505.8A CN201810706505A CN110674411B CN 110674411 B CN110674411 B CN 110674411B CN 201810706505 A CN201810706505 A CN 201810706505A CN 110674411 B CN110674411 B CN 110674411B
- Authority
- CN
- China
- Prior art keywords
- node
- viewpoint
- media
- nodes
- message
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000007246 mechanism Effects 0.000 claims abstract description 14
- 230000008859 change Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 15
- 230000007935 neutral effect Effects 0.000 claims description 14
- 230000006854 communication Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 230000001902 propagating effect Effects 0.000 claims description 5
- 238000007596 consolidation process Methods 0.000 claims description 3
- 230000003203 everyday effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 239000007787 solid Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 239000002085 irritant Substances 0.000 description 1
- 231100000021 irritant Toxicity 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention provides a network public opinion propagation model MI-SEIR (Media and internal relationship-SEIR) model based on two factors of Media propagation and Interpersonal propagation and a propagation method thereof. Wherein the method comprises the following steps: first, an MI-SEIR model is built and the types of nodes in the MI-SEIR model are set. Secondly, setting the attribute of each node in the model, and establishing a message propagation mechanism and an evolution mechanism according to the attribute parameters. And determining the quantity change of various nodes in the model by calculating the viewpoint values of all the nodes at each moment. Finally, a public opinion propagation model which is more in line with real life is obtained.
Description
Technical Field
The invention relates to the field of public opinion analysis, in particular to an MI-SEIR model based on media and interpersonal influence.
Background
With the rapid growth of the internet, people are increasingly inclined to learn about or publish messages on the network. Some messages that are relevant to people can cause intense discussion, and people can also create or change their thoughts when exchanging messages. If the public opinion of society is guided to be negative, the social order and daily life are impacted and destroyed by emotional, false and irritant information in the network public opinion. It is necessary to fully exert the positive influence of the network public opinion on the social order, eliminate the negative influence, strive for the media to guide and monitor the network public opinion, and enhance the research on the network public opinion under the combined action of the media and interpersonal transmission.
At present, the main research is focused on the strengthening effect of media on message propagation and the evolution process of netizen opinions, and few researches are carried out on the opinion change situation and the influence of the opinion change situation on the message propagation process when different opinion groups communicate with each other. The model simulation result provided by the invention combines the SEIR model, the propagation process influenced by media and interpersonal, the node discussion and the interconversion mechanism together, better accords with the public opinion propagation process, and has certain realization value and research significance.
Disclosure of Invention
The invention provides an Internet public opinion transmission model MI-SEIR model influenced by two factors, namely media transmission and interpersonal transmission, based on an SEIR infectious disease model. The model classifies the propagation nodes into three categories of support, neutral and objection according to the viewpoint values of the individual nodes. The nodes have a discussion mechanism, namely a node point value evolution rule is established according to parameters such as self-enforcement degree, influence of the other party, reported content quality of media, media reporting strength, infectivity and the like, and the mutual transformation process of the nodes is realized by changing self point values.
The MI-SEIR model based on media and interpersonal effects comprises the following steps: and establishing a mathematical model of the assembly line workshop scheduling problem.
1) An improved SEIR model is established.
2) The node type of the improved SEIR model is set.
3) And setting the attribute of each node in the model.
4) And establishing a message propagation mechanism and an evolution mechanism.
5) And counting the number of each type of node.
The method for establishing the improved SEIR model in the step 1 comprises the following steps:
the MI-SEIR model based on media and interpersonal effects makes detailed classification of the crowd categories. The susceptible population S represents a person who has not received a message in the public opinion dissemination model. E a And E b The public opinion propagation model respectively represents a person who knows a message from media but does not decide whether to propagate and a person who knows the message through interpersonal relations but does not decide whether to propagate. I is a ，I b ，I c Respectively representing people who have the propagated messages in support, neutral and objection three attitudes. R represents a person who does not propagate the message or a person who has stopped propagating the message.
In step 2, the node type of the improved sei model is set as follows:
the model provided herein has two types of nodes, one being individual nodes and the other being media nodes.
The individual nodes refer to people in the society, each person has three attitudes of objection, neutrality and support to topics, and the channel for each person to receive messages comprises conversations with relatives, friends and colleagues and media messages received every day, such as network, broadcast, newspapers and the like. People with higher position and larger influence are included in the people, and the degree of node of the people is called 'opinion leader' and 'opinion leader'.
The media nodes comprise media such as the Internet, microblogs, forums, televisions and broadcasts, and the media nodes also have three attitudes of support, neutrality and objection to topics. The nodes connected with the media nodes are mostly people with similar opinions. The degree of media nodes is large.
In step 3, the attributes of each node in the model are set as follows:
(1) Observation value O i . The individual's opinion on the message is divided into three attitudes of support, neutral and opposition.
(2) Viewpoint threshold value mu i . The difference between the viewpoint value of the node i and the viewpoint value of the neighbor node is smaller than the viewpoint threshold value, and the other node can get close to the other node from the standpoint, otherwise, the node i is more biased to the standpoint of the node.
(3) Value of relation omega ij . The weight of the relationship between node i and node j. The larger the weight, the more intimate the relationship between the two people.
(4) Influence delta ij . The impact capability of node i on other nodes.
(5) Degree of consolidation σ i . The strength of section i itself.
(6) The mass is reported as v. Richness and quality of media story content.
(7) The force θ is reported. The reported extent of the media to the message. The more media the message is reported on, the faster the message propagates.
(8) Infectivity η. The extent of influence of the media report message.
(9) The attractive force τ. Titles and keywords used when media reporting messages are attractive to netizens. The more attractive the title is to the netizen, the more curious the netizen is, thereby enabling the netizen to join the discussion.
In the step 4, the method for establishing the message propagation mechanism and the evolution mechanism includes:
firstly, a network relation model is established, each node in the network is endowed with a viewpoint value, and initially, the viewpoint values of all the nodes are uniformly distributed on (0, 1). Selecting some nodes with larger node degree as media nodes, and giving the media nodes an observation approaching 0 or 1Point values make their attitudes explicit. Among them, interpersonal message propagation is affected by the magnitude of influence and the degree of robustness. Message dissemination of media is affected by media story content, title appeal, and the like. The propagation process of the message includes the following steps a Evolution to I, from E b Evolution to I, I a ，I b ，I c Communication between three and slave I a ，I b ，I c Evolution to R.
In the step 5, the method for counting the number of the nodes of each type is as follows:
the propagation of the message is calculated according to the view values of the nodes obtained by the evolution rule every time a period of time passes, according to the objection viewpoint value of (0, 0.33) and the neutral viewpoint value of [0.33,0.66 ]]Supporting recalculation of I for a viewpoint value of (0.67, 1) a ，I b ，I c The number of people. Every time period, calculating S and E a 、E b 、I a 、I b 、I c And the number of R.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a model structure diagram of the present invention.
Fig. 2 is a schematic diagram of node degree distribution using a network.
Fig. 3 is a diagram illustrating the number change of each state node.
Detailed Description
The following describes in further detail embodiments of the present invention with reference to the accompanying drawings.
FIG. 1 is a model structure diagram of the present invention. The susceptible population S will have a probability of alpha 1 The message spread by the receiving medium becomes a latent crowd E a Also from the probability α 2 Become a latent crowd E by learning messages through interpersonal relationships b Part of the population will have a probability α 3 Directly converted into immune population R. Latent person E who knows messages from media a And E learning messages from interpersonal relationships b Can become with supportNeutral and against three attitude propagation population I a ，I b ，I c . In the process of transmitting the message, the transmission crowd can carry out thought exchange, and part of the crowd can be converted into relative marketing. Dissemination population I a ，I b ，I c The immune population R will be transformed after losing the interest in the dissemination and discussion of the message.
Fig. 1 shows a model structure diagram of the present invention, wherein the specific steps are as follows:
1. and establishing an improved SEIR model, namely an MI SEIR model.
The MI-SEIR model based on media and interpersonal effects makes detailed classification of the crowd categories. The susceptible group S represents a person who has not received a message in the public opinion dissemination model. E a And E b The public opinion propagation model respectively represents a person who knows a message from media but does not decide whether to propagate and a person who knows the message through interpersonal relations but does not decide whether to propagate. I is a ，I b ，I c Respectively representing people holding propagated messages in support, neutral and against three attitudes. R represents a person who does not propagate the message or a person who has stopped propagating the message.
2. The node type of the improved SEIR model is set.
The model provided herein has two types of nodes, one being individual nodes and the other being media nodes.
The individual nodes refer to people in the society, each person has three attitudes of objection, neutrality and support to topics, and the channel for each person to receive messages comprises conversations with relatives, friends and colleagues and media messages received every day, such as network, broadcast, newspapers and the like. People with higher position and larger influence are included in the people, and the degree of node of the people is called 'opinion leader' and 'opinion leader'.
The media nodes comprise media such as the Internet, microblogs, forums, televisions and broadcasts, and the media nodes also have three attitudes of support, neutrality and objection to topics. The nodes connected with the media nodes are mostly people with similar opinions. The degree of media nodes is large.
3. And setting the attribute of each node in the model.
(1) Observation value O i . The individual's view of the message is divided into three attitudes of support, neutral and object, the range of values is (0, 1), the object is (0, 0.33), and the neutral is [0.33,0.66 ]]And the support is (0.66, 1). In the initial state of the network, the viewpoint values of all nodes except the media node are subject to uniform distribution.
(2) Viewpoint threshold value mu i . The difference between the viewpoint value of the node i and the viewpoint value of the neighbor node is smaller than the viewpoint threshold value, and the other node can get close to the other node from the standpoint, otherwise, the node i is more biased to the standpoint of the node. The value range is (0, 0.5). The larger the view threshold, the more susceptible the node is to being influenced by other nodes to be transformed into other camps.
(3) Value of relation omega ij . The weight of the relationship between node i and node j. The value range is (0, 1). The larger the weight, the more intimate the relationship between the two people.
(4) Influence delta ij . Influence capability of node i on other nodes.
The expression represents the magnitude of the relationship value between the node i and the node j in the sum of the relationship values of all the nodes connected with the node j. The larger the influence of the node is, the more easily the influence is caused on the opinions of other people.
(5) Degree of consolidation σ i . The strength of section i itself.
d i Representing the degree of the node i, and the equation represents the proportion of the degree of the node i to the degree of the largest node in the network. The firmer the individual is, the less susceptible it is to others to change his or her opinion.
(6) The mass is reported as v. Richness and quality of media story content. The value range is (0, 1). The more convincing the content of the media story is, the higher the quality, e.g. a story with video is easier for people to understand the truthfulness of the message, so the content quality is set to 0.8, 0.6 with pictures and 0.4 with only text.
(7) The force θ is reported. The reported extent of the media to the message.
The more media the message is reported on, the faster the message propagates.
(8) Infectivity η. The extent of influence of the media report message.
(9) The attractive force τ. Titles and keywords used when media reporting messages are attractive to netizens. The title is attractive to netizens and can arouse curiosity of netizens, thereby enabling the netizens to join discussions.
4. And establishing a message propagation mechanism and an evolution mechanism.
A) From E a Evolution to I: setting the node j as an individual node and the node i as a media node.
If | O i -O j |＜μ j That is, the difference between the viewpoint values of the node j and the node i is smaller than the viewpoint threshold, which indicates that the two nodes can communicate normally, but the media viewpoint is not easily affected by the individual node. The viewpoint values of the individual nodes are close to the media.
O j (t+1)＝O j (t)+β 1 ×[O i (t)-O j (t)] (1)
Beta in the formula (1) 1 (= θ τ η). For example, when node i supports antisymmetry and node j supports support attitude, and the difference between the two is smaller than the view threshold, then O i (t)-O j (t) < 0, the view value of node j at the next time point gets closer to objection.
If | O i -O j |＞μ j That is, the difference between the viewpoint values of the node j and the node i is greater than the viewpoint threshold, which indicates that the two nodes cannot communicate normally, and the viewpoint of the individual node conflicts with that of the media node, so that the viewpoint value of the individual node is more biased to the original viewpoint value of the individual nodeThe point held is.
O j (t+1)＝O j (t)-β 1 ×[O i (t)-O j (t)] (2)
B) From E b Evolution to I: the process is the message propagation among interpersonal relationships, namely the message passing between individual nodes.
If | O i -O j |＜μ j That is, the node i and the node j can communicate normally, then:
O j (t+1)＝O j (t)+β 2 ×[O i (t)-O j (t)] (3)
beta in the formula (3) 2 (= influence of E) Degree of firmness 。
If | O i -O j |＞μ j That is, the difference between the viewpoint values of the node i and the node j is larger than the viewpoint threshold, and the two cannot communicate normally, the viewpoint value of the node j is more biased toward the viewpoint originally held by the node i rather than approaching the node i. Then:
O j (t+1)＝O j (t)-β 2 ×[O i (t)-O j (t)] (4)
C)I a ，I b ，I c communication among the three: the process of message dissemination is not only that an individual node learns the message from a media node or "opinion leader", but also includes the process of mutual discussion and correction of groups of people with different viewpoints. When people discuss, whether the viewpoint is changed or not and the degree of the change are related to the strength of the self-body of the individual and the influence of the neighbor node on the individual. The larger the influence of the individual is, the higher the position of the individual is, the more the relationship is, the more the message sources are, and the speaking of the individual is more convincing for the neighbor nodes. Therefore, when the communication process of the crowd is simulated, the influence and the solid intensity of the two nodes with communication are compared respectively.
λ j ＝δ ij *exp(-σ j ) (5a)
In the formula (5 a), δ ji Is the magnitude of the influence of node i on node j, σ j Is the degree of robustness of the node j itself.
λ i ＝δ ji *exp(-σ i ) (5b)
In the formula (5 b), δ ji Is the magnitude of the influence of node j on node i, σ i Is the self-consistency of the node i.
If λ i ＞λ j I.e., node i has a greater influence on node j, the viewpoint value of node j changes, while the viewpoint value of node i does not change.
O j (t+1)＝O j (t)+λ j ×[O i (t)-O j (t)] (6)
O i (t+1)＝O i (t) (7)
If λ i ＜λ j I.e., node j has a greater influence on node i, the viewpoint value of node i is considered to the viewpoint value of node j, while the viewpoint value of node j is unchanged.
O i (t+1)＝O i (t)+λ i ×[O j (t)-O i (t)] (8)
O j (t+1)＝O j (t) (9)
If λ i ＝λ j I.e. the influence of node i is the same as that of node j, the viewpoint values of both nodes are close to the viewpoint value of each other.
O j (t+1)＝O j (t)+λ j ×[O i (t)-O j (t)] (10)
O i (t+1)＝O i (t)+λ i ×[O j (t)-O i (t)] (11)
D) From I a ，I b ，I c Evolution to R: after each calculation of viewpoint values of all nodes except the media node, the viewpoint values are compared. The nodes with the observation point values within the range of (0.95, 1) are the firm population with the support attitude and are directly converted into the immune population R, the nodes with the observation point values within the range of (0, 0.05) are the firm population with the objection attitude and are directly converted into the immune population R, and the nodes with the observation point values kept within the range of (0.45, 0.55) are the population with the neutral attitude and are also directly converted into the immune population R in a period of time.
And finally, verifying the correctness of the model through experimental simulation. The node degree distribution of the network is shown in fig. 2, and the degree distribution is power law distribution and conforms to the characteristics of a scale-free network. In the process from the beginning to the end of the message propagation, the number of each state node changes as shown in fig. 3, and the number of people S who do not obtain the message gradually decreases along with the message propagation, and tends to be stable when reaching a certain number. E for obtaining messages from media and interpersonal communication respectively and pending propagation a And E b The variation is not obvious because most people choose to propagate or abandon the person R who becomes a non-propagating message when they know it. Person I with supporting and objecting attitudes a ，I c The number of people I who hold the neutral attitude is increased and then decreased c The slow increase eventually stabilizes. Because people can be influenced by others to stand on the opposite side of self-holding attitude to think when spreading and communicating ideas, and finally the double-sided nature of the message is acknowledged. As the message is spread among people, the situation becomes clearer gradually, people gradually lose the interest in message discussion, and the number of people R who do not spread the message is increased gradually and becomes stable. The number change trend of each state node accords with the public sentiment propagation process in reality, and the model provided by the method is proved to have practical significance.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and it is obvious that those skilled in the art can make various changes and modifications of the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (3)
1. The method for establishing the MI-SEIR model based on media and interpersonal influence is characterized by comprising the following steps of: the MI-SEIR model based on media and interpersonal effects carries out detailed division on crowd categories, wherein susceptible crowd S represents people who do not receive messages in the public opinion propagation model, E a And E b Representing slave media separately in public opinion dissemination modelPersons who know the message but do not decide whether to propagate or not and persons who know the message through interpersonal relationships but do not decide whether to propagate, I a ，I b ，I c Respectively representing persons holding the message propagation with three attitudes of support, neutral and object, R representing persons not propagating the message or persons stopping propagating the message;
the model is provided with two nodes, one is an individual node, the other is a media node, the individual node refers to a crowd in the society, each person has three attitudes of objection, neutrality and support to the message, and the channel for each person to receive the message comprises conversation with relatives, friends and colleagues and network, broadcast and newspaper media messages received every day; people with higher status and larger influence are included in the people, and the people are called as opinion leaders with larger node degree;
the media nodes comprise internet, microblog, forum, television and broadcast media, and the media nodes also have three attitudes of support, neutrality and objection to the message; the nodes connected with the media nodes are mostly people with similar opinions; the degree of the media nodes is very large, and the specific steps comprise:
1) Setting the attribute of each node in the model;
2) Establishing a message propagation mechanism and an evolution mechanism;
3) Counting the number of each type of node;
4) Establishing a message propagation mechanism and an evolution mechanism;
a) Evolution from Ea to I: setting a node j as an individual node and a node i as a media node;
if | O i -O j |＜μ j That is, the difference between the viewpoint values of the node j and the node i is smaller than the viewpoint threshold, which indicates that the two nodes can communicate normally, but the viewpoint of the media is not easily affected by the individual node, so the viewpoint value of the individual node is close to the media,
O j (t+1)＝O j (t)+β 1 ×[O i (t)-O j (t)] (1)
beta in the formula (1) 1 (= θ × τ) (-) η, for example, when node i supports antisynchronization, node j supports supportDegree, the difference between the two is less than the viewpoint threshold, when O i (t)-O j (t) < 0, the viewpoint value of the node j at the next moment is closed to objection;
if | O i -O j |＞μ j That is, the difference between the viewpoint values of the node j and the node i is larger than the viewpoint threshold, which indicates that the two nodes cannot communicate normally, the individual node will conflict with the viewpoint of the media node, so that the viewpoint value of the individual node is more biased to the viewpoint originally held by itself,
O j (t+1)＝O j (t)-β 1 ×[O i (t)-O j (t)] (2)
b) From E b Evolution to I: the process is the message propagation among interpersonal relationships, namely the message transmission between individual nodes;
if | O i -O j |＜μ j That is, the node i and the node j can communicate normally, then:
O j (t+1)＝O j (t)+β 2 ×[O i (t)-O j (t)] (3)
beta in the formula (3) 2 (= influence of E) Degree of firmness ；
If | O i -O j |＞μ j That is, the difference between the viewpoint values of the node i and the node j is greater than the viewpoint threshold, and the two nodes cannot communicate normally, so that the viewpoint value of the node j is more biased to the viewpoint originally held by itself rather than approaching the node i, and then:
O j (t+1)＝O j (t)-β 2 ×[O i (t)-O j (t)] (4)
C)I a ，I b ，I c communication among the three: the process of message dissemination not only allows the individual nodes to learn the messages from the media nodes or the opinion leaders, but also includes the mutual discussion and correction process of people with different viewpoints; when people discuss, whether the viewpoint is changed or not and the degree of the change are related to the self firmness of the individual and the influence of the neighbor node on the individual; the larger the influence of an individual is, the higher the position, the more the relation and the more the message sources are, and the speaking of the individual leads the neighbors of the individual to beThe nodes are more convincing, so when the communication process of the crowd is simulated, the influence and the solid intensity of the two nodes with communication are compared respectively,
λ j ＝δ ij *exp(-σ j ) (5a)
in the formula (5 a), δ ij Is the magnitude of the influence of node i on node j, σ j Is the degree of robustness of the node j itself,
λ i ＝δ ji *exp(-σ i ) (5b)
in the formula (5 b), δ ji Is the magnitude of the influence of node j on node i, σ i The self-strength of the node i;
if λ i ＞λ j I.e., node i has a greater influence on node j, the viewpoint value of node j changes, while the viewpoint value of node i does not change,
O j (t+1)＝O j (t)+λ j ×[O i (t)-O j (t)] (6)
O i (t+1)＝O i (t) (7)
if λ i ＜λ j I.e., node j has a greater influence on node i, the viewpoint value of node i is considered to the viewpoint value of node j, while the viewpoint value of node j is unchanged,
O i (t+1)＝O i (t)+λi×[O j (t)-O i (t)] (8)
O j (t+1)＝O j (t) (9)
if λ i ＝λ j I.e. the influence of the node i is the same as that of the node j, the viewpoint values of the two nodes are close to the viewpoint value of the other node,
O j (t+1)＝O j (t)+λ j ×[O i (t)-O j (t)] (10)
O i (t+1)＝O i (t)+λ i ×[O j (t)-O i (t)] (11)
d) From I a ，I b ，I c Evolution to R: after each calculation of viewpoint values of all nodes except the media node, the viewpoint values are compared with the viewpoint valuesThe nodes in the range of (0.95, 1) are the firm population with the support attitude and are directly converted into the immune population R, the nodes with the viewpoint values in the range of (0, 0.05) are the firm population with the objection attitude and are directly converted into the immune population R, and the nodes with the viewpoint values kept in the range of (0.45, 0.55) are the population with the neutral attitude and are also directly converted into the immune population R in a period of time.
2. A method for building an MI-sei model based on media and interpersonal influences as claimed in claim 1, wherein in said step 3, the attributes of each node in the model are set as follows:
(1) Observation value O i : the individual's view of the message is divided into three attitudes of support, neutral and object, the range of values is (0, 1), the object is (0, 0.33), and the neutral is [0.33,0.66 ]]Support is (0.66, 1);
(2) Viewpoint threshold value mu i : the difference between the viewpoint value of the node i and the viewpoint value of the neighbor node is smaller than the viewpoint threshold value, the node can be drawn to the other side from the standpoint, otherwise, the node is more biased to the standpoint of the node, the value range is (0, 0.5), and the larger the viewpoint threshold value is, the more easily the node is influenced by other nodes and is converted into the other side for marketing;
(3) Value of relation omega ij : the value range of the weight of the relationship between the node i and the node j is (0, 1), and the larger the weight is, the more intimate the relationship between two persons is;
(4) Influence delta ij : influence ability of the node i on other nodes;
(5) Degree of consolidation σ i : the strength of the section i;
(6) Reported mass v: the abundance and quality of the media report content, the value range is (0, 1);
(7) The reported force θ: the reporting degree of the media to the message, the more the number of the media reporting the message, the faster the message is spread;
(8) Infectivity η: the extent of influence of the media story message;
(9) Attraction force τ: the title and keywords used in media reporting messages appeal to netizens, and the title appeal to netizens can arouse curiosity of netizens, thereby enabling netizens to join discussions.
3. The method for building an MI-sei model based on media and interpersonal influences as claimed in claim 1, wherein the step 5, the method for counting the number of each type of nodes is as follows:
every time a period of time passes, the viewpoint values of the nodes are calculated according to the evolution rule, and according to the deprecated viewpoint value of (0, 0.33), the neutral viewpoint value of [0.33,0.66 ]]Supporting recalculation of I for a viewpoint value of (0.67, 1) a ，I b ，I c The number of groups of people, each time period, the S, E are calculated a ，E b ，I，I a ，I b ，I c And the number of R.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810706505.8A CN110674411B (en) | 2018-07-02 | 2018-07-02 | Public opinion propagation model based on media and interpersonal influence and propagation method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810706505.8A CN110674411B (en) | 2018-07-02 | 2018-07-02 | Public opinion propagation model based on media and interpersonal influence and propagation method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110674411A CN110674411A (en) | 2020-01-10 |
| CN110674411B true CN110674411B (en) | 2023-03-24 |
Family
ID=69065930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810706505.8A Active CN110674411B (en) | 2018-07-02 | 2018-07-02 | Public opinion propagation model based on media and interpersonal influence and propagation method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110674411B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127427A (en) * | 2016-06-20 | 2016-11-16 | 西安建筑科技大学 | Multiple target transport path combined optimization method based on plague Epidemic Model |
| CN107798623A (en) * | 2017-10-26 | 2018-03-13 | 江南大学 | Media intervene lower three points of opinion colonies network public-opinion propagation model |
| CN107918610A (en) * | 2016-10-09 | 2018-04-17 | 郑州大学 | A kind of microblogging propagation model towards Time Perception |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170300657A1 (en) * | 2016-04-14 | 2017-10-19 | Virginia Polytechnic Institute And State University | Computerized Event Simulation Using Synthetic Populations |
-
2018
- 2018-07-02 CN CN201810706505.8A patent/CN110674411B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127427A (en) * | 2016-06-20 | 2016-11-16 | 西安建筑科技大学 | Multiple target transport path combined optimization method based on plague Epidemic Model |
| CN107918610A (en) * | 2016-10-09 | 2018-04-17 | 郑州大学 | A kind of microblogging propagation model towards Time Perception |
| CN107798623A (en) * | 2017-10-26 | 2018-03-13 | 江南大学 | Media intervene lower three points of opinion colonies network public-opinion propagation model |
Non-Patent Citations (1)
| Title |
|---|
| "基于改良SEIR 模型的微博话题式信息传播研究";崔金栋等;《情报科学》;20171231;第24-29页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110674411A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hayes et al. | One click, many meanings: Interpreting paralinguistic digital affordances in social media | |
| Wang | User experiences in live video streaming: a netnography analysis | |
| Sprecher et al. | Thebusinessoflove. com: Relationship initiation at Internet matchmaking services | |
| Plesner | Studying sideways: Displacing the problem of power in research interviews with sociologists and journalists | |
| Costa et al. | Microblogging in technology enhanced learning: A use-case inspection of PPE summer school 2008 | |
| Griffiths et al. | Unleashing corporate communications via social media: A UK study of brand management and conversations with customers | |
| Zhang et al. | Network public opinion propagation model based on the influence of media and interpersonal communication | |
| Gilmore et al. | Networking in SMEs: findings from Australia and Ireland | |
| Mayangsari et al. | Understanding communication among parents and teachers in WhatsApp. Case study in Bandung, Indonesia | |
| Toff et al. | Avoiding the news: Reluctant audiences for journalism | |
| Schober et al. | Young immunologists of Europe, unite! | |
| Stebner et al. | Totally transparent: A qualitative study about the impact of farm tours on bloggers | |
| CN110674411B (en) | Public opinion propagation model based on media and interpersonal influence and propagation method thereof | |
| Rahmawan | Selebtwits: micro-celebrity practitioners in Indonesian twittersphere | |
| Kaptein et al. | Nice to know you: familiarity and influence in social networks | |
| Masuku et al. | An assessment to the use of Facebook as a communication tool by Midlands State University students from 2012 to 2013 | |
| Jefferis et al. | The importance of Twitter in the professional development of digitally-engaged head teachers | |
| Mostmans et al. | “I would never post that”: Children, moral sensitivity and online disclosure | |
| Rodriguez | Taboo to trendy: How is OnlyFans breaking boundaries and creating narratives | |
| Wen et al. | Information seeking and responding networks in physical gatherings: A case study of academic conferences in twitter | |
| Deckert | Co-animation of and resistance to the construction of witness, victim, and perpetrator identities in forensic interviews with children | |
| Burns et al. | How Girls Are Using Social Network Sites and Online Communities to Combat Sexism | |
| Cha | The Twitter ties that retweet: Information diffusion in social movements | |
| Gui | The influence of celebrity politician’s tiktok towards young voters’ voting behaviour | |
| Ramadan et al. | Understanding Online Brand Relationships in Western Asia: The Case of Lebanon and Saudi Arabia |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |